Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     typically
    0.41
    seated
    0.41
     الت
    0.38
    Reporter
    0.38
    Pane
    0.37
     seated
    0.37
    Shown
    0.37
    Reporting
    0.37
    typically
    0.37
     लटका
    0.37
    POSITIVE LOGITS
    窸
    0.51
     fok
    0.46
     foc
    0.41
    洴
    0.41
     Fok
    0.40
     Verne
    0.39
     opini
    0.38
     Expressions
    0.38
     rupt
    0.38
     Phal
    0.38
    Act Density 0.000%

    No Known Activations